In this research, we propose a learning-based plug-and-play prior framework for parallel MRI reconstruction which extends the framework to its data-adaptive variant and provides an end-to-end reconstruction scheme.
We demonstrate that a deep plug-and-play prior framework for parallel MRI reconstruction with a regularization that adapts to the data itself results in excellent reconstruction accuracy and outperforms the clinical gold standard GRAPPA method.
In this research, we propose to exploit the spatial gradient of the image formation model to improve the conditioning of parallel imaging reconstruction and to reduce the magnitude of g-factor artifact. We derive the constraint from the acquisition model that induce a coupling between the signal intensity at a voxel, and the signal intensity at other neighboring voxels. These additional constraints improve the conditioning of the parallel imaging reconstruction by helping to disambiguate aliasing artifact.